{"id":"https://openalex.org/W4403413357","doi":"https://doi.org/10.1145/3674805.3686695","title":"A Transformer-based Approach for Augmenting Software Engineering Chatbots Datasets","display_name":"A Transformer-based Approach for Augmenting Software Engineering Chatbots Datasets","publication_year":2024,"publication_date":"2024-10-15","ids":{"openalex":"https://openalex.org/W4403413357","doi":"https://doi.org/10.1145/3674805.3686695"},"language":"en","primary_location":{"id":"doi:10.1145/3674805.3686695","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3674805.3686695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033095642","display_name":"Ahmad Abdellatif","orcid":"https://orcid.org/0000-0003-1863-9147"},"institutions":[{"id":"https://openalex.org/I168635309","display_name":"University of Calgary","ror":"https://ror.org/03yjb2x39","country_code":"CA","type":"education","lineage":["https://openalex.org/I168635309"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ahmad Abdellatif","raw_affiliation_strings":["University of Calgary, Canada"],"raw_orcid":"https://orcid.org/0000-0003-1863-9147","affiliations":[{"raw_affiliation_string":"University of Calgary, Canada","institution_ids":["https://openalex.org/I168635309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102847449","display_name":"Khaled Badran","orcid":"https://orcid.org/0000-0003-2293-3656"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Khaled Badran","raw_affiliation_strings":["Concordia University, Canada"],"raw_orcid":"https://orcid.org/0000-0003-2293-3656","affiliations":[{"raw_affiliation_string":"Concordia University, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023951345","display_name":"Diego Elias Costa","orcid":"https://orcid.org/0000-0001-7084-2594"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Diego Elias Costa","raw_affiliation_strings":["Concordia University, Canada"],"raw_orcid":"https://orcid.org/0000-0001-7084-2594","affiliations":[{"raw_affiliation_string":"Concordia University, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049727493","display_name":"Emad Shihab","orcid":"https://orcid.org/0000-0003-1285-9878"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Emad Shihab","raw_affiliation_strings":["Concordia University, Canada"],"raw_orcid":"https://orcid.org/0000-0003-1285-9878","affiliations":[{"raw_affiliation_string":"Concordia University, Canada","institution_ids":["https://openalex.org/I60158472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"359","last_page":"370"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12128","display_name":"AI in Service Interactions","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7235249280929565},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5724756121635437},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4774359166622162},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.471737265586853},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19126099348068237},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17566341161727905},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.15351003408432007}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7235249280929565},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5724756121635437},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4774359166622162},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.471737265586853},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19126099348068237},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17566341161727905},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.15351003408432007},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3674805.3686695","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3674805.3686695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2028602070","https://openalex.org/W2038721957","https://openalex.org/W2406204547","https://openalex.org/W2546705944","https://openalex.org/W2781728735","https://openalex.org/W2786860129","https://openalex.org/W2795319782","https://openalex.org/W2884229567","https://openalex.org/W2911420856","https://openalex.org/W2945826489","https://openalex.org/W2953484861","https://openalex.org/W2954554621","https://openalex.org/W2955449396","https://openalex.org/W2967531795","https://openalex.org/W2983149555","https://openalex.org/W2986068180","https://openalex.org/W3034999214","https://openalex.org/W3088041916","https://openalex.org/W3088195551","https://openalex.org/W3091658513","https://openalex.org/W3098348021","https://openalex.org/W3100742171","https://openalex.org/W3102985954","https://openalex.org/W3111275476","https://openalex.org/W3184561823","https://openalex.org/W3211801722","https://openalex.org/W4284709233","https://openalex.org/W4312565886","https://openalex.org/W4313563595","https://openalex.org/W4400581939"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032"],"abstract_inverted_index":{"Background:":[0],"The":[1],"adoption":[2],"of":[3,19,24,57,82,133,197],"chatbots":[4,77,199],"into":[5],"software":[6,26,75,100,145],"development":[7,27],"tasks":[8],"has":[9],"become":[10],"increasingly":[11],"popular":[12],"among":[13],"practitioners,":[14],"driven":[15],"by":[16,121],"the":[17,25,34,114,131,135,139,150,158,182,195],"advantages":[18],"cost":[20],"reduction":[21],"and":[22,85,127,200],"acceleration":[23],"process.":[28],"Chatbots":[29],"understand":[30],"users\u2019":[31],"queries":[32,123,162],"through":[33,124],"Natural":[35],"Language":[36],"Understanding":[37],"component":[38],"(NLU).":[39],"To":[40],"yield":[41],"reasonable":[42],"performance,":[43,160],"NLUs":[44],"have":[45],"to":[46,98,117,204],"be":[47],"trained":[48],"with":[49,62,113,163],"extensive,":[50],"high-quality":[51,71],"datasets,":[52],"that":[53,68,189],"express":[54],"a":[55,70,119],"multitude":[56],"ways":[58],"users":[59],"may":[60],"interact":[61],"chatbots.":[63,210],"However,":[64],"previous":[65],"studies":[66],"show":[67],"creating":[69],"training":[72],"dataset":[73,120],"for":[74,181,208],"engineering":[76,101,146],"is":[78],"expensive":[79],"in":[80,89,156,177],"terms":[81],"both":[83],"resources":[84],"time.":[86],"Aims:":[87],"Therefore,":[88],"this":[90],"paper,":[91],"we":[92],"present":[93],"an":[94],"automated":[95],"transformer-based":[96],"approach":[97,106,137,152],"augment":[99,118],"chatbot":[102],"datasets.":[103,147],"Method:":[104],"Our":[105],"combines":[107],"traditional":[108],"natural":[109],"language":[110],"processing":[111],"techniques":[112,207],"BART":[115],"transformer":[116],"generating":[122],"synonym":[125],"replacement":[126],"paraphrasing.":[128],"We":[129,187],"evaluate":[130],"impact":[132],"using":[134,143],"augmentation":[136,151,206],"on":[138],"Rasa":[140],"NLU\u2019s":[141],"performance":[142,196],"three":[144],"Results:":[148],"Overall,":[149],"shows":[153],"promising":[154],"results":[155],"improving":[157],"Rasa\u2019s":[159,175],"augmenting":[161],"varying":[164],"sentence":[165],"structures":[166],"while":[167],"preserving":[168],"their":[169,198],"original":[170],"semantics.":[171],"Furthermore,":[172],"it":[173],"increases":[174],"confidence":[176],"its":[178],"intent":[179],"classification":[180],"correctly":[183],"classified":[184],"intents.":[185],"Conclusions:":[186],"believe":[188],"our":[190],"study":[191],"helps":[192],"practitioners":[193],"improve":[194],"guides":[201],"future":[202],"research":[203],"propose":[205],"SE":[209]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}